status: PhD Researcher @ COSIC, KU Leuven

Working towards openly verifiable perceptual hash functions.

I focus on the cryptographic aspects of perceptual hash functions, specifically the formalisation of their properties, as well as their evaluation and design. Current technologies, widely used for content moderation and detecting copyright infringement, often rely on security-through-obscurity. My research pursues the design of openly verifiable algorithms, which I believe are a strict requirement for large-scale deployments.

01. About

I am a first-year PhD student and FWO PhD Fellow at COSIC, KU Leuven, interested in perceptual hash functions from a cryptographic and mathematical perspective. In particular, I focus on designing openly verifiable systems rather than relying on security-through-obscurity. I am fortunate to be advised by Prof. Bart Preneel and Dr. Diane Leblanc-Albarel.

Previously, I obtained a Master’s degree in Mathematics from Ghent University. In my thesis, supervised by Prof. Jan De Beule (Vrije Universiteit Brussel) and Prof. Leo Storme (Ghent University), I studied cryptographic topics using techniques from finite geometry. Through this work, I was able to sharpen the lower bound on the number of non-bent components of crooked quadratic (APN) functions.

02. Research

2026

White-Box Attacks on PhotoDNA Perceptual Hash Function

Maxime Deryck, Diane Leblanc-Albarel, Bart Preneel

To appear at IEEE Symposium on Security & Privacy, May 2027

ePrint

Cryptography meets Finite Geometry

2026

This thesis highlights the interplay between cryptography and finite geometry. In the part on symmetric cryptography, novel results regarding the number of non-bent components of quadratic APN functions are formulated.

PDF

Master's Thesis

More on research View all publications & projects →